Back to skills
SKILL.md
Taste Skill
ASecurityUse when building, styling, optimizing, and auditing taste skill components, responsive layouts, design systems, and frontend state.
- 5 stars
- 0 votes
- 0 copies
- 0 views
- Added September 27, 2026
Works with
Security analysis
100/100npx -y skills add Harmitx7/tribunal-kit --skill taste-skill --agent claude-codeAre you the author of Taste Skill?
Add the live security badge to your README. It updates with every re-scan.
[](https://www.skillsdirectory.com/skills/harmitx7-taste-skill)---
name: taste-skill
description: "Use when building, styling, optimizing, and auditing taste skill components, responsive layouts, design systems, and frontend state."
version: 6.0.0
last-updated: 2026-09-29
skills:
- better-ui
- impeccable
- baseline-ui
tools: Read, Grep, Glob, Bash, Edit, Write
scripts-binding:
- .agent/scripts/lint_runner.js
- .agent/scripts/verify_all.js
---
# Taste Skill β Senior Design Taste & Anti-Slop Discipline
## Mandatory Pre-Flight Context Inspection
Before reading, generating, or refactoring code in the `taste-skill` domain, inspect these 5 critical parameters:
1. **System Boundaries & Dependencies**: Verify that all required dependencies exist in target package manifests and environment paths.
2. **Runtime Context & Platform Invariants**: Confirm target platform constraints (Node.js, Browser, Mobile OS, Edge runtime) before applying APIs.
3. **Execution Guardrails**: Identify potential side-effects, state mutations, and unhandled asynchronous exceptions.
4. **Validation & Type Contracts**: Validate input data schemas and strict type constraints across all module interfaces.
5. **Observability & Proof of Execution**: Ensure execution produces tangible verification signals (terminal output, tests, metrics).
## Activation Boundaries
- **Activate when:** Use when building, styling, optimizing, and auditing taste skill components, responsive layouts, design systems, and frontend state.
- **DO NOT activate when:** The task falls outside the `taste-skill` domain or is managed by a different dedicated specialist agent.
## π Multi-Pass Execution Protocol
| Pass | Phase | Core Action | Adaptive Depth |
|:---|:---|:---|:---|
| **Pass 1** | **Understand** | Deconstruct the user's explicit objective, implicit requirements, and platform constraints. | Fast / Standard / Deep |
| **Pass 2** | **Plan** | Decompose task into smallest logical steps; map dependencies, affected files, and tool calls. | Standard / Deep |
| **Pass 3** | **Execute** | Implement solution with production-grade craft, zero placeholders, and strict typing. | All Modes |
| **Pass 4** | **Verify** | Run linters, unit tests, or compiler checks to validate structural correctness. | All Modes |
| **Pass 5** | **Attack & Falsify** | Perform adversarial search for edge-case failures, counterexamples, race conditions, and traps. | Standard / Deep |
| **Pass 6** | **Harden** | Eliminate discovered friction, optimize performance, and harden error boundaries. | Standard / Deep |
| **Pass 7** | **Quality Gate** | Enforce Verification-Before-Completion (VBC) with concrete terminal proof before finalizing. | All Modes |
---
## π οΈ Technical Architecture & Reference Recipes
---
## The 5 Rules of Design Taste
### 1. Banned AI Visual ClichΓ©s (Zero Tolerance)
- β Purple/violet gradient backgrounds (`from-purple-600 to-indigo-600`).
- β Glowing neon borders on every card element.
- β Floating 3D spheres or generic iridescent mesh gradients.
- β Identical Bento Box 3-column grids on every page.
### 2. High-Fidelity Typography
- Typography accounts for 80% of interface perception.
- Display headings must use negative tracking (`-0.025em`) and balanced text wrapping (`text-wrap: balance`).
- Body text line length MUST be bounded to `65ch` max width.
### 3. Spatial System Strictness
- Never use arbitrary `px` paddings or margins (`margin-top: 17px`).
- Enforce strict 8px spatial grid math (`4px`, `8px`, `12px`, `16px`, `24px`, `32px`, `48px`, `64px`).
### 4. Tactile Micro-Feedback
- All interactive controls MUST respond to press with `transform: scale(0.97)` on `:active` with transition duration $\le 160\text{ms}$.
### 5. Multi-Layer Depth Over Flat Lines
- Replace harsh black borders with multi-layer ambient drop shadows and subtle 8% opacity surface outlines.
## π¨ Edge-Case & Failure Mode Matrix
| Scenario | Risk | Production Mitigation |
|:---|:---|:---|
| **Empty or Null Inputs** | Unhandled exception or unexpected rendering collapse | Enforce fallback guards, optional chaining, and explicit empty state handlers |
| **Network Timeout / Latency** | Hanging operations or duplicate side-effects | Implement bounded abort controllers, exponential backoff, and idempotency keys |
| **Concurrency / Race Conditions** | Stale state overwrite or inconsistent data mutations | Use atomic transactions, mutex locking, or cancel-on-resubmit controls |
| **Invalid Schema / Malformed Payload** | Downstream runtime errors or security injection | Validate boundary payloads with Zod/Pydantic schemas prior to execution |
| **Resource / Memory Saturation** | OOM errors, frame drops, or memory leaks | Clean up listeners, cancel active timers, and enforce pagination/virtualization |
## π€ LLM-Specific Traps Table
| Anti-Pattern | What AI Commonly Does Wrong | What Is Actually Correct |
|:---|:---|:---|
| **Uncontrolled Re-render Loop** | Mutating state inside render bodies or omitting hook dependencies | Wrap effects with explicit deps and isolate reactive derivations in useMemo |
| **Accessibility Neglect** | Interactive <div> without role="button", tabIndex, or onKeyDown | Use semantic <button> or provide ARIA role, keyboard handlers, and focus ring |
| **Layout Shift Flash** | Images/dynamic content without aspect-ratio or explicit dimensions | Enforce aspect-ratio or skeleton placeholders to guarantee zero CLS |
## ποΈ Tribunal Verification & Guardrails
**Active Reviewers:** `frontend-reviewer` Β· `type-safety` Β· `ui-ux-auditor` Β· `complexity-reviewer`
**Slash Command:** `/review` or `/tribunal-full`
### π¬ Evidence Standard (Tri-State Verification)
Every finding, audit statement, or completion claim must classify its factual certainty:
- **`[OBSERVED]`**: Directly confirmed in the codebase or verified via executed terminal command.
- **`[INFERRED]`**: Logically deduced from code patterns, architectural data flow, or schema relations.
- **`[UNVERIFIED]`**: Speculative hypothesis or runtime possibility requiring active testing or measurement.
### β
Pre-Flight Self-Audit Checklist
```
β
Are all component props strictly typed with zero implicit "any"?
β
Are responsive breakpoints, fluid typography, and optical balance verified?
β
Is accessibility (ARIA labels, keyboard navigation, contrast ratio >= 4.5:1) validated?
β
Are re-renders minimized and state lifecycles cleanly separated?
β
Did I verify all imported UI components and icon sets actually exist?
```
### π Verification-Before-Completion (VBC) Protocol
**CRITICAL:** You must follow a strict "evidence-based closeout" state machine.
- β **Forbidden:** Declaring a task complete because the output "looks correct."
- β
**Required:** You are explicitly forbidden from finalizing any task without providing **concrete evidence** (terminal output, passing test suites, compiler success, or equivalent operational proof) that your output works as intended.
Attribution
Comments
Loading commentsβ¦